2025-06-13 18:45:53,711 - INFO - ================================================================================ - [multilabel_classify.py:101:log_section] 2025-06-13 18:45:53,711 - INFO - = ๐Ÿ“Œ INITIALIZING TRAINING ENVIRONMENT = - [multilabel_classify.py:102:log_section] 2025-06-13 18:45:53,711 - INFO - ================================================================================ - [multilabel_classify.py:105:log_section] 2025-06-13 18:45:53,711 - INFO - ๐Ÿš€ Setting up data paths and environment variables... - [multilabel_classify.py:3916:main] 2025-06-13 18:45:53,712 - INFO - ๐Ÿ“‚ Using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3922:main] 2025-06-13 18:45:53,712 - INFO - ๐Ÿ› ๏ธ Command-line Arguments: - [multilabel_classify.py:369:print_args] 2025-06-13 18:45:53,712 - INFO - ๐Ÿ”น output_dir: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b ๐Ÿ”น source_url: XURLs.MIMIC4_DEMO ๐Ÿ”น data: mimic4_icd10_full ๐Ÿ”น logfile: classification_log ๐Ÿ”น base_dir: ../tmp/MIMIC4_DEMO ๐Ÿ”น hub_model_id: deb101/mistral-7b-instruct-v0.3-mimic4-adapt ๐Ÿ”น model_name: mistralai/Mistral-7B-Instruct-v0.3 ๐Ÿ”น max_length: 512 ๐Ÿ”น do_fresh_training: True ๐Ÿ”น load_from_checkpoint: False ๐Ÿ”น task: multilabel-classify ๐Ÿ”น num_train_epochs: 1 ๐Ÿ”น per_device_train_batch_size: 8 ๐Ÿ”น per_device_eval_batch_size: 8 ๐Ÿ”น metric_for_best_model: precision_at_15 ๐Ÿ”น learning_rate: 0.0001 ๐Ÿ”น final_lr_scheduling: 1e-06 ๐Ÿ”น warmup_steps: 500 ๐Ÿ”น logfile_path: ../tmp/logs/classification_log_2025-06-13_18-45-53.log ๐Ÿ”น source: /home/ubuntu/.xcube/data/mimic4_demo - [multilabel_classify.py:370:print_args] 2025-06-13 18:45:53,712 - INFO - โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž– - [multilabel_classify.py:371:print_args] 2025-06-13 18:45:53,722 - INFO - ๐Ÿš€ Quick Git Info: ๐Ÿ“ xcube | ๐ŸŒฟ plant | ๐Ÿ” 0bd4309 | ๐Ÿ‘ค Debjyoti Saha Roy | โšก MIXED (1 staged, 2 unstaged) | ๐Ÿ”ฌ git show 0bd4309 - [multilabel_classify.py:3928:main] 2025-06-13 18:45:53,722 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:45:53,723 - INFO - + โœจ LOADING DATASETS + - [multilabel_classify.py:102:log_section] 2025-06-13 18:45:53,723 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:45:53,723 - INFO - ๐Ÿ“Š Loading main datasets.... - [multilabel_classify.py:3931:main] 2025-06-13 18:46:02,259 - INFO - ๐Ÿ” Total unique labels in dataset: 7942 - [multilabel_classify.py:3707:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,272 - INFO - ๐Ÿงช Attempt 1: Sampled 122 rows covering 863 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,282 - INFO - ๐Ÿงช Attempt 2: Sampled 122 rows covering 816 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,291 - INFO - ๐Ÿงช Attempt 3: Sampled 122 rows covering 885 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,300 - INFO - ๐Ÿงช Attempt 4: Sampled 122 rows covering 828 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,309 - INFO - ๐Ÿงช Attempt 5: Sampled 122 rows covering 879 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,317 - INFO - ๐Ÿงช Attempt 6: Sampled 122 rows covering 852 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,326 - INFO - ๐Ÿงช Attempt 7: Sampled 122 rows covering 838 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,335 - INFO - ๐Ÿงช Attempt 8: Sampled 122 rows covering 851 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,343 - INFO - ๐Ÿงช Attempt 9: Sampled 122 rows covering 825 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,351 - INFO - ๐Ÿงช Attempt 10: Sampled 122 rows covering 833 labels. - [multilabel_classify.py:3721:sample_df_with_full_label_coverage] 2025-06-13 18:46:02,356 - INFO - ๐Ÿ› ๏ธ Fixing missing labels: 7109 remaining... - [multilabel_classify.py:3754:sample_df_with_full_label_coverage] 2025-06-13 18:49:30,886 - INFO - โœ… Added 1648 rows to achieve full label coverage. - [multilabel_classify.py:3786:sample_df_with_full_label_coverage] 2025-06-13 18:49:30,889 - INFO - ๐Ÿ“Š Final total labels: 7942 - [multilabel_classify.py:3789:sample_df_with_full_label_coverage] 2025-06-13 18:49:30,889 - INFO - โœ… Final row count: 1770 (Valid: 420, Not-valid: 1350) - [multilabel_classify.py:3797:sample_df_with_full_label_coverage] 2025-06-13 18:49:31,659 - INFO - ******************************************************************************** - [multilabel_classify.py:101:log_section] 2025-06-13 18:49:31,659 - INFO - * ๐ŸŒŸ STARTING MULTI_LABEL CLASSIFICATION MODEL TRAINING * - [multilabel_classify.py:102:log_section] 2025-06-13 18:49:31,659 - INFO - ******************************************************************************** - [multilabel_classify.py:105:log_section] 2025-06-13 18:49:31,659 - INFO - ๐Ÿ” Loaded authentication token from environment - [multilabel_classify.py:3958:main] 2025-06-13 18:49:31,659 - INFO - ๐Ÿท๏ธ Hub Model ID for this Classification task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3962:main] 2025-06-13 18:49:31,659 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:101:log_section] 2025-06-13 18:49:31,659 - INFO - - ๐Ÿ“‹ MODEL EXISTENCE CHECK - - [multilabel_classify.py:102:log_section] 2025-06-13 18:49:31,659 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:105:log_section] 2025-06-13 18:49:31,659 - INFO - ๐Ÿ” Checking model existence locally and on Hugging Face Hub... - [multilabel_classify.py:3822:check_model_existence] 2025-06-13 18:49:31,659 - INFO - โŒ Model not found locally at: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3829:check_model_existence] 2025-06-13 18:49:31,726 - INFO - โœ… Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3841:check_model_existence] 2025-06-13 18:49:31,726 - INFO - ๐Ÿ“ Model exists either locally or on Hub - [multilabel_classify.py:3867:check_model_existence] 2025-06-13 18:49:31,726 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:49:31,726 - INFO - + โœจ STARTING FRESH TRAINING + - [multilabel_classify.py:102:log_section] 2025-06-13 18:49:31,727 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:49:31,727 - INFO - ๐Ÿ”„ Starting fresh training (either forced or model not found)... - [multilabel_classify.py:3975:main] 2025-06-13 18:49:31,738 - WARNING - Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured. - [_login.py:415:_login] 2025-06-13 18:49:31,738 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:49:31,738 - INFO - + โœจ LOADING BASE MODEL + - [multilabel_classify.py:102:log_section] 2025-06-13 18:49:31,738 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:49:31,738 - INFO - ๐Ÿ“ฅ Loading pretrained model and tokenizer... - [multilabel_classify.py:4007:main] 2025-06-13 18:49:31,738 - INFO - ๐Ÿš€ Starting model and tokenizer loading process... - [multilabel_classify.py:1579:load_base_model_and_tokenizer] 2025-06-13 18:49:31,739 - INFO - ๐Ÿ“Š Quantization config: 4-bit, nf4, double_quant, bfloat16 - [multilabel_classify.py:1588:load_base_model_and_tokenizer] 2025-06-13 18:49:31,739 - INFO - ๐Ÿ”ค Loading tokenizer for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1592:load_base_model_and_tokenizer] 2025-06-13 18:49:32,680 - INFO - ๐Ÿ” Checking if deb101/mistral-7b-instruct-v0.3-mimic4-adapt is a PEFT model... - [multilabel_classify.py:1603:load_base_model_and_tokenizer] 2025-06-13 18:49:32,735 - INFO - โœ… Detected PEFT model. Base model: mistralai/Mistral-7B-Instruct-v0.3 - [multilabel_classify.py:1607:load_base_model_and_tokenizer] 2025-06-13 18:49:32,735 - INFO - ๐Ÿ” Loading model configuration for mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1615:load_base_model_and_tokenizer] 2025-06-13 18:49:32,810 - INFO - Model type: mistral, Architectures: ['MistralForCausalLM'] - [multilabel_classify.py:1630:load_base_model_and_tokenizer] 2025-06-13 18:49:32,810 - INFO - ๐Ÿง  Loading base model: mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1698:load_base_model_and_tokenizer] 2025-06-13 18:49:33,322 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). - [modeling.py:991:get_balanced_memory] 2025-06-13 18:49:38,581 - INFO - ๐Ÿงฉ Loading PEFT adapters for deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1718:load_base_model_and_tokenizer] 2025-06-13 18:49:39,365 - INFO - ๐Ÿ”ง Before enabling PEFT adapters - [multilabel_classify.py:1720:load_base_model_and_tokenizer] 2025-06-13 18:49:39,367 - INFO - ๐Ÿ“Š trainable params: 0 || all params: 7,254,839,296 || trainable%: 0.0000 - [multilabel_classify.py:160:log_print_output] 2025-06-13 18:49:39,370 - INFO - Enabled gradients for parameters: ['base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight'] - [multilabel_classify.py:1730:load_base_model_and_tokenizer] 2025-06-13 18:49:39,370 - INFO - ๐Ÿ”ง After enabling PEFT adapters - [multilabel_classify.py:1731:load_base_model_and_tokenizer] 2025-06-13 18:49:39,372 - INFO - ๐Ÿ“Š trainable params: 6,815,744 || all params: 7,254,839,296 || trainable%: 0.0939 - [multilabel_classify.py:160:log_print_output] 2025-06-13 18:49:39,374 - INFO - โœ… Model and tokenizer successfully loaded! - [multilabel_classify.py:1769:load_base_model_and_tokenizer] 2025-06-13 18:49:39,374 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:49:39,374 - INFO - + โœจ DATA PREPROCESSING + - [multilabel_classify.py:102:log_section] 2025-06-13 18:49:39,374 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:49:39,374 - INFO - ๐Ÿ”„ Loading and preprocessing training data... - [multilabel_classify.py:4017:main] 2025-06-13 18:49:39,553 - INFO - Total number of labels: 7942 - [multilabel_classify.py:1172:preprocess_data] 2025-06-13 18:49:39,553 - INFO - Rare labels (freq < 50): 7817 - [multilabel_classify.py:1173:preprocess_data] 2025-06-13 18:49:39,553 - INFO - Not rare labels (freq >= 50): 125 - [multilabel_classify.py:1174:preprocess_data] 2025-06-13 18:49:39,553 - INFO - Label partitions and classes saved to ../tmp/MIMIC4_DEMO/labels_partition.json - [multilabel_classify.py:1175:preprocess_data] 2025-06-13 18:50:36,704 - INFO - The size of training set: 8393 - [multilabel_classify.py:1271:preprocess_data] 2025-06-13 18:50:36,704 - INFO - The size of Evaluation set: 2528 - [multilabel_classify.py:1272:preprocess_data] 2025-06-13 18:50:37,110 - INFO - Number of unique ICD-10 codes: 7942 - [multilabel_classify.py:4023:main] 2025-06-13 18:50:37,112 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:50:37,112 - INFO - + โœจ MODEL INITIALIZATION + - [multilabel_classify.py:102:log_section] 2025-06-13 18:50:37,112 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:50:37,112 - INFO - ๐Ÿง  Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [multilabel_classify.py:4026:main] 2025-06-13 18:50:37,113 - INFO - ๐Ÿฅ๐Ÿ“Š Creating MultilabelICDClassifier - Standard multilabel medical classifier! ๐Ÿ”ฌ๐Ÿ’ซ - [multilabel_classify.py:860:define_model] 2025-06-13 18:50:37,113 - INFO - Will now start to create Multilabel-Classification Model from the base model - [multilabel_classify.py:565:__init__] 2025-06-13 18:50:37,117 - INFO - ๐Ÿ“Š trainable params: 6,815,744 || all params: 3,765,178,368 || trainable%: 0.1810 - [multilabel_classify.py:619:compute_trainable_params] 2025-06-13 18:50:38,856 - INFO - Creating the Multi-Label Classification Model from base model mistralai/Mistral-7B-Instruct-v0.3 completed!!! - [multilabel_classify.py:607:__init__] 2025-06-13 18:50:38,860 - INFO - ๐Ÿ“Š trainable params: 171,532,417 || all params: 3,929,895,041 || trainable%: 4.3648 - [multilabel_classify.py:619:compute_trainable_params] 2025-06-13 18:50:38,860 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:50:38,860 - INFO - + โœจ TRAINING PREPARATION + - [multilabel_classify.py:102:log_section] 2025-06-13 18:50:38,860 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:50:38,861 - INFO - โš™๏ธ Preparing training components and optimizers... - [multilabel_classify.py:4033:main] 2025-06-13 18:50:38,945 - INFO - ๐Ÿ–ฅ๏ธ Device: NVIDIA GH200 480GB - [multilabel_classify.py:1019:log_training_configuration] 2025-06-13 18:50:38,945 - INFO - ๐Ÿ”‹ CUDA Available: True - [multilabel_classify.py:1022:log_training_configuration] 2025-06-13 18:50:38,945 - INFO - ๐Ÿ’พ CUDA Device Count: 1 - [multilabel_classify.py:1023:log_training_configuration] 2025-06-13 18:50:38,947 - INFO - ๐Ÿ“‹ Training Configuration ๐Ÿ“‹ +----------+-----------------------------+------------------------------------------------------------------+ | ๐ŸŒŸ Emoji | ๐Ÿท๏ธ Parameter | ๐Ÿ“Š Value | +----------+-----------------------------+------------------------------------------------------------------+ | ๐Ÿ“ | Output Directory | ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b | | ๐Ÿ” | Training Epochs | 1 | | ๐Ÿ‹๏ธ | Train Batch Size | 8 | | ๐Ÿ” | Eval Batch Size | 8 | | ๐Ÿ“Š | Gradient Accumulation Steps | 4 | | ๐Ÿš€ | Learning Rate | 0.0001 | | ๐ŸŒ… | Warmup Steps | 500 | | ๐Ÿ’พ | Save Strategy | epoch | | ๐Ÿ’พ | Save Total Limit | 10 | | ๐Ÿ“Š | Evaluation Strategy | epoch | | ๐ŸŽฏ | Best Model Metric | precision_at_15 | | ๐Ÿ“ | Logging Strategy | steps (every 10 steps) | | ๐ŸŒ | Push to Hub | True | | ๐ŸŒ | Hub Model ID | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify | | ๐Ÿ”ข | Steps per Epoch | 262 | | ๐Ÿ”ข | Total Training Steps | 262 | | ๐Ÿ”ข | Evaluation Steps | 316 | | ๐Ÿ“Š | Training Dataset Size | 8393 samples ๐Ÿ‹๏ธ | | ๐Ÿ“Š | Evaluation Dataset Size | 2528 samples ๐Ÿ” | +----------+-----------------------------+------------------------------------------------------------------+ - [multilabel_classify.py:1011:log_training_args] 2025-06-13 18:50:38,947 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 18:50:38,948 - INFO - + โœจ MODEL TRAINING + - [multilabel_classify.py:102:log_section] 2025-06-13 18:50:38,948 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 18:50:38,948 - INFO - ๐Ÿ‹๏ธ Starting model training process... - [multilabel_classify.py:4055:main] 2025-06-13 18:50:38,998 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt in Custom Trainer - [multilabel_classify.py:2340:__init__] 2025-06-13 18:50:39,246 - INFO - ๐Ÿš€ Starting Training... - [multilabel_classify.py:1994:on_train_begin] 2025-06-13 18:51:01,764 - INFO - ๐Ÿš‚ Training Metrics (Step 10) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.6752 | +---------------+----------+ | grad_norm | 7.27432 | +---------------+----------+ | learning_rate | 2e-06 | +---------------+----------+ | epoch | 0.038095 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:51:21,360 - INFO - ๐Ÿš‚ Training Metrics (Step 20) ๐Ÿš‚ +---------------+---------+ | Metric | Value | +===============+=========+ | loss | 0.3475 | +---------------+---------+ | grad_norm | 2.94909 | +---------------+---------+ | learning_rate | 4e-06 | +---------------+---------+ | epoch | 0.07619 | +---------------+---------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:51:40,988 - INFO - ๐Ÿš‚ Training Metrics (Step 30) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0737 | +---------------+----------+ | grad_norm | 0.276477 | +---------------+----------+ | learning_rate | 6e-06 | +---------------+----------+ | epoch | 0.114286 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:52:00,566 - INFO - ๐Ÿš‚ Training Metrics (Step 40) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0233 | +---------------+----------+ | grad_norm | 0.104187 | +---------------+----------+ | learning_rate | 8e-06 | +---------------+----------+ | epoch | 0.152381 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:52:20,179 - INFO - ๐Ÿš‚ Training Metrics (Step 50) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0282 | +---------------+----------+ | grad_norm | 0.154837 | +---------------+----------+ | learning_rate | 1e-05 | +---------------+----------+ | epoch | 0.190476 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:52:39,823 - INFO - ๐Ÿš‚ Training Metrics (Step 60) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.027 | +---------------+----------+ | grad_norm | 0.136466 | +---------------+----------+ | learning_rate | 1.2e-05 | +---------------+----------+ | epoch | 0.228571 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:52:59,512 - INFO - ๐Ÿš‚ Training Metrics (Step 70) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0244 | +---------------+----------+ | grad_norm | 0.029749 | +---------------+----------+ | learning_rate | 1.4e-05 | +---------------+----------+ | epoch | 0.266667 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:53:19,196 - INFO - ๐Ÿš‚ Training Metrics (Step 80) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0234 | +---------------+----------+ | grad_norm | 0.042736 | +---------------+----------+ | learning_rate | 1.6e-05 | +---------------+----------+ | epoch | 0.304762 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:53:38,910 - INFO - ๐Ÿš‚ Training Metrics (Step 90) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0235 | +---------------+----------+ | grad_norm | 0.035706 | +---------------+----------+ | learning_rate | 1.8e-05 | +---------------+----------+ | epoch | 0.342857 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:53:58,615 - INFO - ๐Ÿš‚ Training Metrics (Step 100) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0243 | +---------------+----------+ | grad_norm | 0.230328 | +---------------+----------+ | learning_rate | 2e-05 | +---------------+----------+ | epoch | 0.380952 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:54:18,318 - INFO - ๐Ÿš‚ Training Metrics (Step 110) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.023 | +---------------+----------+ | grad_norm | 0.011574 | +---------------+----------+ | learning_rate | 2.2e-05 | +---------------+----------+ | epoch | 0.419048 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:54:38,052 - INFO - ๐Ÿš‚ Training Metrics (Step 120) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0223 | +---------------+----------+ | grad_norm | 0.01187 | +---------------+----------+ | learning_rate | 2.4e-05 | +---------------+----------+ | epoch | 0.457143 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:54:57,782 - INFO - ๐Ÿš‚ Training Metrics (Step 130) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0234 | +---------------+----------+ | grad_norm | 0.008039 | +---------------+----------+ | learning_rate | 2.6e-05 | +---------------+----------+ | epoch | 0.495238 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:55:17,523 - INFO - ๐Ÿš‚ Training Metrics (Step 140) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0233 | +---------------+----------+ | grad_norm | 0.007428 | +---------------+----------+ | learning_rate | 2.8e-05 | +---------------+----------+ | epoch | 0.533333 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:55:37,253 - INFO - ๐Ÿš‚ Training Metrics (Step 150) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0227 | +---------------+----------+ | grad_norm | 0.025854 | +---------------+----------+ | learning_rate | 3e-05 | +---------------+----------+ | epoch | 0.571429 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:55:56,990 - INFO - ๐Ÿš‚ Training Metrics (Step 160) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0218 | +---------------+----------+ | grad_norm | 0.015084 | +---------------+----------+ | learning_rate | 3.2e-05 | +---------------+----------+ | epoch | 0.609524 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:56:16,703 - INFO - ๐Ÿš‚ Training Metrics (Step 170) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0216 | +---------------+----------+ | grad_norm | 0.011318 | +---------------+----------+ | learning_rate | 3.4e-05 | +---------------+----------+ | epoch | 0.647619 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:56:36,435 - INFO - ๐Ÿš‚ Training Metrics (Step 180) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0231 | +---------------+----------+ | grad_norm | 0.021338 | +---------------+----------+ | learning_rate | 3.6e-05 | +---------------+----------+ | epoch | 0.685714 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:56:56,191 - INFO - ๐Ÿš‚ Training Metrics (Step 190) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0236 | +---------------+----------+ | grad_norm | 0.004745 | +---------------+----------+ | learning_rate | 3.8e-05 | +---------------+----------+ | epoch | 0.72381 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:57:15,942 - INFO - ๐Ÿš‚ Training Metrics (Step 200) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0231 | +---------------+----------+ | grad_norm | 0.025924 | +---------------+----------+ | learning_rate | 4e-05 | +---------------+----------+ | epoch | 0.761905 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:57:35,695 - INFO - ๐Ÿš‚ Training Metrics (Step 210) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0222 | +---------------+----------+ | grad_norm | 0.007095 | +---------------+----------+ | learning_rate | 4.2e-05 | +---------------+----------+ | epoch | 0.8 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:57:55,463 - INFO - ๐Ÿš‚ Training Metrics (Step 220) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0225 | +---------------+----------+ | grad_norm | 0.012384 | +---------------+----------+ | learning_rate | 4.4e-05 | +---------------+----------+ | epoch | 0.838095 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:58:15,215 - INFO - ๐Ÿš‚ Training Metrics (Step 230) ๐Ÿš‚ +---------------+---------+ | Metric | Value | +===============+=========+ | loss | 0.0238 | +---------------+---------+ | grad_norm | 0.00828 | +---------------+---------+ | learning_rate | 4.6e-05 | +---------------+---------+ | epoch | 0.87619 | +---------------+---------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:58:34,964 - INFO - ๐Ÿš‚ Training Metrics (Step 240) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0222 | +---------------+----------+ | grad_norm | 0.006233 | +---------------+----------+ | learning_rate | 4.8e-05 | +---------------+----------+ | epoch | 0.914286 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:58:54,736 - INFO - ๐Ÿš‚ Training Metrics (Step 250) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0232 | +---------------+----------+ | grad_norm | 0.011117 | +---------------+----------+ | learning_rate | 5e-05 | +---------------+----------+ | epoch | 0.952381 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:59:14,504 - INFO - ๐Ÿš‚ Training Metrics (Step 260) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.023 | +---------------+----------+ | grad_norm | 0.008961 | +---------------+----------+ | learning_rate | 5.2e-05 | +---------------+----------+ | epoch | 0.990476 | +---------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 18:59:19,754 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2445:_save] 2025-06-13 18:59:19,756 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2450:_save] 2025-06-13 18:59:19,757 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262: +---------+-------------------+------------+ | Index | Saved File | Size | +=========+===================+============+ | 1 | training_args.bin | 0.01 MB | +---------+-------------------+------------+ | 2 | model.safetensors | 4600.97 MB | +---------+-------------------+------------+ | 3 | config.json | 0.00 MB | +---------+-------------------+------------+ - [multilabel_classify.py:2467:_save] 2025-06-13 18:59:20,381 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2352:evaluate] 2025-06-13 19:12:32,601 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.274921 | +-------------------------------+----------+ | eval_recall_at_5 | 0.063731 | +-------------------------------+----------+ | eval_precision_at_8 | 0.253956 | +-------------------------------+----------+ | eval_recall_at_8 | 0.090858 | +-------------------------------+----------+ | eval_precision_at_15 | 0.190533 | +-------------------------------+----------+ | eval_recall_at_15 | 0.122413 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.003718 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.001292 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.004302 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.002289 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.004905 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.00478 | +-------------------------------+----------+ | eval_not_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_not_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_not_rare_precision | 0 | +-------------------------------+----------+ | eval_not_rare_recall | 0 | +-------------------------------+----------+ | eval_not_rare_precision_at_5 | 0.274209 | +-------------------------------+----------+ | eval_not_rare_recall_at_5 | 0.168014 | +-------------------------------+----------+ | eval_not_rare_precision_at_8 | 0.254005 | +-------------------------------+----------+ | eval_not_rare_recall_at_8 | 0.239598 | +-------------------------------+----------+ | eval_not_rare_precision_at_15 | 0.190585 | +-------------------------------+----------+ | eval_not_rare_recall_at_15 | 0.324765 | +-------------------------------+----------+ | eval_loss | 0.020932 | +-------------------------------+----------+ - [multilabel_classify.py:2207:on_evaluate] 2025-06-13 19:12:36,537 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2445:_save] 2025-06-13 19:12:36,538 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2450:_save] 2025-06-13 19:12:36,540 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262: +---------+--------------------+------------+ | Index | Saved File | Size | +=========+====================+============+ | 1 | training_args.bin | 0.01 MB | +---------+--------------------+------------+ | 2 | optimizer.pt | 1308.77 MB | +---------+--------------------+------------+ | 3 | model.safetensors | 4600.97 MB | +---------+--------------------+------------+ | 4 | scaler.pt | 0.00 MB | +---------+--------------------+------------+ | 5 | config.json | 0.00 MB | +---------+--------------------+------------+ | 6 | scheduler.pt | 0.00 MB | +---------+--------------------+------------+ | 7 | trainer_state.json | 0.00 MB | +---------+--------------------+------------+ | 8 | rng_state.pth | 0.01 MB | +---------+--------------------+------------+ - [multilabel_classify.py:2467:_save] 2025-06-13 19:12:37,957 - INFO - ๐Ÿ“‚ Loading best model from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2519:_load_best_model] 2025-06-13 19:12:37,957 - INFO - ๐Ÿ–ฅ๏ธ Model is on device: cuda:0 - [multilabel_classify.py:2529:_load_best_model] 2025-06-13 19:12:38,014 - INFO - ๐Ÿ”‘ Key order comparison: +---------+--------------------------------------------+--------------------------------------------------------------------------------------+ | Index | Saved state_dict Keys | Model state_dict Keys | +=========+============================================+======================================================================================+ | 1 | attention.in_proj_bias | boost_mul | +---------+--------------------------------------------+--------------------------------------------------------------------------------------+ | 2 | attention.in_proj_weight | boost_add | +---------+--------------------------------------------+--------------------------------------------------------------------------------------+ | 3 | attention.out_proj.bias | base_model.base_model.model.model.embed_tokens.weight | +---------+--------------------------------------------+--------------------------------------------------------------------------------------+ | 4 | attention.out_proj.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight | +---------+--------------------------------------------+--------------------------------------------------------------------------------------+ | 5 | base_model.base_model.model.lm_head.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax | +---------+--------------------------------------------+--------------------------------------------------------------------------------------+ - [multilabel_classify.py:2553:_load_best_model] 2025-06-13 19:12:39,020 - INFO - โœ… Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262/model.safetensors - [multilabel_classify.py:2570:_load_best_model] 2025-06-13 19:12:39,059 - INFO - โœ”๏ธ Weight for boost_mul matches between saved and loaded state_dict - [multilabel_classify.py:2582:_load_best_model] 2025-06-13 19:12:39,091 - INFO - โœ”๏ธ Weight for boost_add matches between saved and loaded state_dict - [multilabel_classify.py:2582:_load_best_model] 2025-06-13 19:12:39,108 - INFO - ๐Ÿš‚ Training Metrics (Step 262) ๐Ÿš‚ +--------------------------+----------+ | Metric | Value | +==========================+==========+ | train_runtime | 1319.86 | +--------------------------+----------+ | train_samples_per_second | 6.359 | +--------------------------+----------+ | train_steps_per_second | 0.199 | +--------------------------+----------+ | total_flos | 0 | +--------------------------+----------+ | train_loss | 0.062579 | +--------------------------+----------+ | epoch | 0.998095 | +--------------------------+----------+ - [multilabel_classify.py:2188:on_log] 2025-06-13 19:12:39,108 - INFO - โœจ Training Completed! โœจ - [multilabel_classify.py:2061:on_train_end] 2025-06-13 19:12:39,183 - INFO - ๐Ÿ“Š Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/train_loss_plot.png' - [multilabel_classify.py:2257:on_train_end] 2025-06-13 19:12:39,237 - INFO - ๐Ÿ“Š Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_loss_plot.png' - [multilabel_classify.py:2271:on_train_end] 2025-06-13 19:12:39,297 - INFO - ๐Ÿ“Š Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_precision_at_15_plot.png' - [multilabel_classify.py:2292:on_train_end] 2025-06-13 19:12:39,298 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] 2025-06-13 19:12:39,298 - INFO - + โœจ MODEL SAVING + - [multilabel_classify.py:102:log_section] 2025-06-13 19:12:39,298 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] 2025-06-13 19:12:39,298 - INFO - ๐Ÿ’พ Saving trained model and pushing to Hugging Face Hub... - [multilabel_classify.py:4069:main] 2025-06-13 19:12:39,298 - INFO - ๐Ÿ“ Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3045:save_and_push] 2025-06-13 19:12:40,623 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2445:_save] 2025-06-13 19:12:40,625 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2450:_save] 2025-06-13 19:12:40,626 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b: +---------+-------------------------------+------------+ | Index | Saved File | Size | +=========+===============================+============+ | 1 | eval_loss_plot.png | 0.02 MB | +---------+-------------------------------+------------+ | 2 | training_args.bin | 0.01 MB | +---------+-------------------------------+------------+ | 3 | model.safetensors | 4600.97 MB | +---------+-------------------------------+------------+ | 4 | config.json | 0.00 MB | +---------+-------------------------------+------------+ | 5 | train_loss_plot.png | 0.02 MB | +---------+-------------------------------+------------+ | 6 | eval_precision_at_15_plot.png | 0.03 MB | +---------+-------------------------------+------------+ - [multilabel_classify.py:2467:_save] 2025-06-13 19:12:44,632 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2445:_save] 2025-06-13 19:12:44,634 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2450:_save] 2025-06-13 19:12:44,635 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b: +---------+-------------------------------+------------+ | Index | Saved File | Size | +=========+===============================+============+ | 1 | eval_loss_plot.png | 0.02 MB | +---------+-------------------------------+------------+ | 2 | training_args.bin | 0.01 MB | +---------+-------------------------------+------------+ | 3 | model.safetensors | 4600.97 MB | +---------+-------------------------------+------------+ | 4 | config.json | 0.00 MB | +---------+-------------------------------+------------+ | 5 | train_loss_plot.png | 0.02 MB | +---------+-------------------------------+------------+ | 6 | eval_precision_at_15_plot.png | 0.03 MB | +---------+-------------------------------+------------+ - [multilabel_classify.py:2467:_save] 2025-06-13 19:14:09,684 - INFO - ๐Ÿ’พ Model saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3049:save_and_push] 2025-06-13 19:14:09,714 - INFO - ๐Ÿ–Œ๏ธ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3053:save_and_push]